Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    涉及到
    -0.07
     Về
    -0.07
    普遍存在
    -0.07
    ערך
    -0.07
    /tag
    -0.07
    奶奶
    -0.07
    ,ev
    -0.07
    ﱉ
    -0.07
    得到
    -0.06
     compliment
    -0.06
    POSITIVE LOGITS
    红线
    0.07
    参与者
    0.07
     footing
    0.07
     Keystone
    0.07
    )?;↵
    0.07
     Nationwide
    0.07
     omitted
    0.06
    yii
    0.06
    FFFFFFFF
    0.06
     stri
    0.06
    Act Density 0.066%

    No Known Activations